Token Classification
Transformers
Safetensors
deberta-v2
Generated from Trainer
pii-detection
indian-pii
Instructions to use Vaibhav3311v/deberta-pii-owndlp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Vaibhav3311v/deberta-pii-owndlp with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="Vaibhav3311v/deberta-pii-owndlp")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("Vaibhav3311v/deberta-pii-owndlp") model = AutoModelForTokenClassification.from_pretrained("Vaibhav3311v/deberta-pii-owndlp", device_map="auto") - Notebooks
- Google Colab
- Kaggle
deberta-pii-owndlp
Fine-tuned DeBERTa-v3-base model for PII detection, with specific tuning for Indian identifiers: Aadhaar, PAN, GSTIN, IFSC, and RuPay credit cards, along with standard PII categories (names, emails, phone numbers, addresses, etc).
Verified working on:
- Aadhaar numbers
- PAN numbers
- RuPay card numbers
- Person names, organizations, emails
Verified via manual sanity checks on real test sentences containing these entity types, with confidence scores of 0.90+ across all categories.
- Downloads last month
- 24
Model tree for Vaibhav3311v/deberta-pii-owndlp
Base model
microsoft/deberta-v3-base